© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241281
    Prev
    Next
    INDEX
    Explanations

    abelian, scalar, integer, uniform, straight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KNN
    0.42
     Designed
    0.37
    Designed
    0.36
    簡單
    0.35
    驕
    0.35
     :-)
    0.35
    ‑
    0.34
    
    0.33
     simplic
    0.33
    FAX
    0.33
    POSITIVE LOGITS
     genom
    0.38
     ὁ
    0.36
    過ご
    0.36
     répart
    0.36
     délais
    0.36
     spent
    0.35
     projekt
    0.35
     rxjs
    0.35
     săptăm
    0.35
    屼
    0.35
    Activations Density 0.006%

    No Known Activations